Diffusers documentation
LongCatImageTransformer2DModel
快速入门
推理
使用扩散流水线
适配器与个性化
优化与扩展
模块化 Diffusers
训练与微调
资源
贡献
API
主要类
模块化
加载器
模型
概述AutoModel
ControlNets
Transformers
AceStepTransformer1DModelAllegroTransformer3DModelAnyFlowFARTransformer3DModelAnyFlowTransformer3DModelAuraFlowTransformer2DModelBriaFibo2Transformer2DModelBriaFiboTransformer2DModelBriaTransformer2DModelChromaTransformer2DModelChronoEditTransformer3DModelCogVideoXTransformer3DModelCogView3PlusTransformer2DModelCogView4Transformer2DModelConsisIDTransformer3DModelCosmos3OmniTransformerCosmosTransformer3DModelDiTTransformer2DModelEasyAnimateTransformer3DModelErnieImageTransformer2DModelFlux2Transformer2DModelFlux3Transformer2DModelFluxTransformer2DModelGlmImageTransformer2DModelHeliosTransformer3DModelHiDreamImageTransformer2DModelHunyuanDiT2DModelHunyuanImageTransformer2DModelHunyuanVideo15Transformer3DModelHunyuanVideoTransformer3DModelIdeogram4Transformer2DModelJoyImageEditPlusTransformer3DModelJoyImageEditTransformer3DModelKandinsky 6 TransformersKandinskyS2VTransformer3DModelKrea2Transformer2DModelLatteTransformer3DModelLongCatImageTransformer2DModelLTX2VideoTransformer3DModelLTXVideoTransformer3DModelLumina2Transformer2DModelLuminaNextDiT2DModelMiniMaxH3ImageTransformer2DModelMiniMaxH3Transformer3DModelMiniMaxMusic3Transformer1DModelMochiTransformer3DModelMotifVideoTransformer3DModelOmniGenTransformer2DModelOvisImageTransformer2DModelPAN2Transformer3DModelPixArtTransformer2DModelPriorTransformerQwenImage21Transformer2DModelQwenImageTransformer2DModelRFD4ProteinaAutoencoderRFD4ProteinaTransformerSanaTransformer2DModelSanaVideoTransformer3DModelSanaWMLTX2RefinerTransformer3DModelSanaWMTransformer3DModelSD3Transformer2DModelSkyReelsV2Transformer3DModelStableAudio3DiTModelStableAudioDiTModelTransformer2DModelTransformerTemporalModelWanAnimate2Transformer3DModelWanAnimateTransformer3DModelWanTransformer3DModelZImageTransformer2DModel
UNets
VAEs
管道
调度器
内部类
You are viewing main version, which requires installation from source. If you'd like
regular pip install, checkout the latest stable version (v0.43.0).
LongCatImageTransformer2DModel
可以使用以下代码片段加载该模型。
from diffusers import LongCatImageTransformer2DModel
transformer = LongCatImageTransformer2DModel.from_pretrained("meituan-longcat/LongCat-Image ", subfolder="transformer", dtype=torch.bfloat16)LongCatImageTransformer2DModel
class diffusers.LongCatImageTransformer2DModel
< source >( patch_size: int = 1in_channels: int = 64num_layers: int = 19num_single_layers: int = 38attention_head_dim: int = 128num_attention_heads: int = 24joint_attention_dim: int = 3584pooled_projection_dim: int = 3584axes_dims_rope: list[int] = [16, 56, 56] )
Longcat-Image 中引入的 Transformer 模型。
forward
< source >( hidden_states: Tensorencoder_hidden_states: Tensor = Nonetimestep: LongTensor = Noneimg_ids: Tensor = Nonetxt_ids: Tensor = Noneguidance: Tensor = Nonereturn_dict: bool = True )
参数
- hidden_states(形状为
(batch size, channel, height, width)的torch.FloatTensor)— 输入的hidden_states。 - encoder_hidden_states (
torch.FloatTensor,形状为(batch size, sequence_len, embed_dims)) — 要使用的条件嵌入(由输入条件(例如提示词)计算得出的嵌入)。 - timestep (
torch.LongTensor) — 用于指示去噪步骤。 - img_ids (
torch.Tensor) — 用于计算旋转位置嵌入的图像位置 ID。 - txt_ids (
torch.Tensor) — 用于计算旋转位置嵌入的文本位置 ID。 - guidance (
torch.Tensor, 可选) — 用于模型引导蒸馏变体的引导尺度嵌入。 - return_dict (
bool,可选,默认为True) — 是否返回~models.transformer_2d.Transformer2DModelOutput而不是普通的元组。
前向方法。